summaryrefslogtreecommitdiffstats
path: root/drivers/nvdimm/pmem.c
blob: 7e88cd24238051d5414aa5b513239657cd4904a4 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Persistent Memory Driver
 *
 * Copyright (c) 2014-2015, Intel Corporation.
 * Copyright (c) 2015, Christoph Hellwig <hch@lst.de>.
 * Copyright (c) 2015, Boaz Harrosh <boaz@plexistor.com>.
 */

#include <linux/blkdev.h>
#include <linux/pagemap.h>
#include <linux/hdreg.h>
#include <linux/init.h>
#include <linux/platform_device.h>
#include <linux/set_memory.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/badblocks.h>
#include <linux/memremap.h>
#include <linux/vmalloc.h>
#include <linux/blk-mq.h>
#include <linux/pfn_t.h>
#include <linux/slab.h>
#include <linux/uio.h>
#include <linux/dax.h>
#include <linux/nd.h>
#include <linux/mm.h>
#include <asm/cacheflush.h>
#include "pmem.h"
#include "btt.h"
#include "pfn.h"
#include "nd.h"

static struct device *to_dev(struct pmem_device *pmem)
{
	/*
	 * nvdimm bus services need a 'dev' parameter, and we record the device
	 * at init in bb.dev.
	 */
	return pmem->bb.dev;
}

static struct nd_region *to_region(struct pmem_device *pmem)
{
	return to_nd_region(to_dev(pmem)->parent);
}

static phys_addr_t to_phys(struct pmem_device *pmem, phys_addr_t offset)
{
	return pmem->phys_addr + offset;
}

static sector_t to_sect(struct pmem_device *pmem, phys_addr_t offset)
{
	return (offset - pmem->data_offset) >> SECTOR_SHIFT;
}

static phys_addr_t to_offset(struct pmem_device *pmem, sector_t sector)
{
	return (sector << SECTOR_SHIFT) + pmem->data_offset;
}

static void pmem_mkpage_present(struct pmem_device *pmem, phys_addr_t offset,
		unsigned int len)
{
	phys_addr_t phys = to_phys(pmem, offset);
	unsigned long pfn_start, pfn_end, pfn;

	/* only pmem in the linear map supports HWPoison */
	if (is_vmalloc_addr(pmem->virt_addr))
		return;

	pfn_start = PHYS_PFN(phys);
	pfn_end = pfn_start + PHYS_PFN(len);
	for (pfn = pfn_start; pfn < pfn_end; pfn++) {
		struct page *page = pfn_to_page(pfn);

		/*
		 * Note, no need to hold a get_dev_pagemap() reference
		 * here since we're in the driver I/O path and
		 * outstanding I/O requests pin the dev_pagemap.
		 */
		if (test_and_clear_pmem_poison(page))
			clear_mce_nospec(pfn);
	}
}

static void pmem_clear_bb(struct pmem_device *pmem, sector_t sector, long blks)
{
	if (blks == 0)
		return;
	badblocks_clear(&pmem->bb, sector, blks);
	if (pmem->bb_state)
		sysfs_notify_dirent(pmem->bb_state);
}

static long __pmem_clear_poison(struct pmem_device *pmem,
		phys_addr_t offset, unsigned int len)
{
	phys_addr_t phys = to_phys(pmem, offset);
	long cleared = nvdimm_clear_poison(to_dev(pmem), phys, len);

	if (cleared > 0) {
		pmem_mkpage_present(pmem, offset, cleared);
		arch_invalidate_pmem(pmem->virt_addr + offset, len);
	}
	return cleared;
}

static blk_status_t pmem_clear_poison(struct pmem_device *pmem,
		phys_addr_t offset, unsigned int len)
{
	long cleared = __pmem_clear_poison(pmem, offset, len);

	if (cleared < 0)
		return BLK_STS_IOERR;

	pmem_clear_bb(pmem, to_sect(pmem, offset), cleared >> SECTOR_SHIFT);
	if (cleared < len)
		return BLK_STS_IOERR;
	return BLK_STS_OK;
}

static void write_pmem(void *pmem_addr, struct page *page,
		unsigned int off, unsigned int len)
{
	unsigned int chunk;
	void *mem;

	while (len) {
		mem = kmap_atomic(page);
		chunk = min_t(unsigned int, len, PAGE_SIZE - off);
		memcpy_flushcache(pmem_addr, mem + off, chunk);
		kunmap_atomic(mem);
		len -= chunk;
		off = 0;
		page++;
		pmem_addr += chunk;
	}
}

static blk_status_t read_pmem(struct page *page, unsigned int off,
		void *pmem_addr, unsigned int len)
{
	unsigned int chunk;
	unsigned long rem;
	void *mem;

	while (len) {
		mem = kmap_atomic(page);
		chunk = min_t(unsigned int, len, PAGE_SIZE - off);
		rem = copy_mc_to_kernel(mem + off, pmem_addr, chunk);
		kunmap_atomic(mem);
		if (rem)
			return BLK_STS_IOERR;
		len -= chunk;
		off = 0;
		page++;
		pmem_addr += chunk;
	}
	return BLK_STS_OK;
}

static blk_status_t pmem_do_read(struct pmem_device *pmem,
			struct page *page, unsigned int page_off,
			sector_t sector, unsigned int len)
{
	blk_status_t rc;
	phys_addr_t pmem_off = to_offset(pmem, sector);
	void *pmem_addr = pmem->virt_addr + pmem_off;

	if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
		return BLK_STS_IOERR;

	rc = read_pmem(page, page_off, pmem_addr, len);
	flush_dcache_page(page);
	return rc;
}

static blk_status_t pmem_do_write(struct pmem_device *pmem,
			struct page *page, unsigned int page_off,
			sector_t sector, unsigned int len)
{
	phys_addr_t pmem_off = to_offset(pmem, sector);
	void *pmem_addr = pmem->virt_addr + pmem_off;

	if (unlikely(is_bad_pmem(&pmem->bb, sector, len))) {
		blk_status_t rc = pmem_clear_poison(pmem, pmem_off, len);

		if (rc != BLK_STS_OK)
			return rc;
	}

	flush_dcache_page(page);
	write_pmem(pmem_addr, page, page_off, len);

	return BLK_STS_OK;
}

static void pmem_submit_bio(struct bio *bio)
{
	int ret = 0;
	blk_status_t rc = 0;
	bool do_acct;
	unsigned long start;
	struct bio_vec bvec;
	struct bvec_iter iter;
	struct pmem_device *pmem = bio->bi_bdev->bd_disk->private_data;
	struct nd_region *nd_region = to_region(pmem);

	if (bio->bi_opf & REQ_PREFLUSH)
		ret = nvdimm_flush(nd_region, bio);

	do_acct = blk_queue_io_stat(bio->bi_bdev->bd_disk->queue);
	if (do_acct)
		start = bio_start_io_acct(bio);
	bio_for_each_segment(bvec, bio, iter) {
		if (op_is_write(bio_op(bio)))
			rc = pmem_do_write(pmem, bvec.bv_page, bvec.bv_offset,
				iter.bi_sector, bvec.bv_len);
		else
			rc = pmem_do_read(pmem, bvec.bv_page, bvec.bv_offset,
				iter.bi_sector, bvec.bv_len);
		if (rc) {
			bio->bi_status = rc;
			break;
		}
	}
	if (do_acct)
		bio_end_io_acct(bio, start);

	if (bio->bi_opf & REQ_FUA)
		ret = nvdimm_flush(nd_region, bio);

	if (ret)
		bio->bi_status = errno_to_blk_status(ret);

	bio_endio(bio);
}

static int pmem_rw_page(struct block_device *bdev, sector_t sector,
		       struct page *page, enum req_op op)
{
	struct pmem_device *pmem = bdev->bd_disk->private_data;
	blk_status_t rc;

	if (op_is_write(op))
		rc = pmem_do_write(pmem, page, 0, sector, thp_size(page));
	else
		rc = pmem_do_read(pmem, page, 0, sector, thp_size(page));
	/*
	 * The ->rw_page interface is subtle and tricky.  The core
	 * retries on any error, so we can only invoke page_endio() in
	 * the successful completion case.  Otherwise, we'll see crashes
	 * caused by double completion.
	 */
	if (rc == 0)
		page_endio(page, op_is_write(op), 0);

	return blk_status_to_errno(rc);
}

/* see "strong" declaration in tools/testing/nvdimm/pmem-dax.c */
__weak long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
		long nr_pages, enum dax_access_mode mode, void **kaddr,
		pfn_t *pfn)
{
	resource_size_t offset = PFN_PHYS(pgoff) + pmem->data_offset;
	sector_t sector = PFN_PHYS(pgoff) >> SECTOR_SHIFT;
	unsigned int num = PFN_PHYS(nr_pages) >> SECTOR_SHIFT;
	struct badblocks *bb = &pmem->bb;
	sector_t first_bad;
	int num_bad;

	if (kaddr)
		*kaddr = pmem->virt_addr + offset;
	if (pfn)
		*pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags);

	if (bb->count &&
	    badblocks_check(bb, sector, num, &first_bad, &num_bad)) {
		long actual_nr;

		if (mode != DAX_RECOVERY_WRITE)
			return -EIO;

		/*
		 * Set the recovery stride is set to kernel page size because
		 * the underlying driver and firmware clear poison functions
		 * don't appear to handle large chunk(such as 2MiB) reliably.
		 */
		actual_nr = PHYS_PFN(
			PAGE_ALIGN((first_bad - sector) << SECTOR_SHIFT));
		dev_dbg(pmem->bb.dev, "start sector(%llu), nr_pages(%ld), first_bad(%llu), actual_nr(%ld)\n",
				sector, nr_pages, first_bad, actual_nr);
		if (actual_nr)
			return actual_nr;
		return 1;
	}

	/*
	 * If badblocks are present but not in the range, limit known good range
	 * to the requested range.
	 */
	if (bb->count)
		return nr_pages;
	return PHYS_PFN(pmem->size - pmem->pfn_pad - offset);
}

static const struct block_device_operations pmem_fops = {
	.owner =		THIS_MODULE,
	.submit_bio =		pmem_submit_bio,
	.rw_page =		pmem_rw_page,
};

static int pmem_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
				    size_t nr_pages)
{
	struct pmem_device *pmem = dax_get_private(dax_dev);

	return blk_status_to_errno(pmem_do_write(pmem, ZERO_PAGE(0), 0,
				   PFN_PHYS(pgoff) >> SECTOR_SHIFT,
				   PAGE_SIZE));
}

static long pmem_dax_direct_access(struct dax_device *dax_dev,
		pgoff_t pgoff, long nr_pages, enum dax_access_mode mode,
		void **kaddr, pfn_t *pfn)
{
	struct pmem_device *pmem = dax_get_private(dax_dev);

	return __pmem_direct_access(pmem, pgoff, nr_pages, mode, kaddr, pfn);
}

/*
 * The recovery write thread started out as a normal pwrite thread and
 * when the filesystem was told about potential media error in the
 * range, filesystem turns the normal pwrite to a dax_recovery_write.
 *
 * The recovery write consists of clearing media poison, clearing page
 * HWPoison bit, reenable page-wide read-write permission, flush the
 * caches and finally write.  A competing pread thread will be held
 * off during the recovery process since data read back might not be
 * valid, and this is achieved by clearing the badblock records after
 * the recovery write is complete. Competing recovery write threads
 * are already serialized by writer lock held by dax_iomap_rw().
 */
static size_t pmem_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff,
		void *addr, size_t bytes, struct iov_iter *i)
{
	struct pmem_device *pmem = dax_get_private(dax_dev);
	size_t olen, len, off;
	phys_addr_t pmem_off;
	struct device *dev = pmem->bb.dev;
	long cleared;

	off = offset_in_page(addr);
	len = PFN_PHYS(PFN_UP(off + bytes));
	if (!is_bad_pmem(&pmem->bb, PFN_PHYS(pgoff) >> SECTOR_SHIFT, len))
		return _copy_from_iter_flushcache(addr, bytes, i);

	/*
	 * Not page-aligned range cannot be recovered. This should not
	 * happen unless something else went wrong.
	 */
	if (off || !PAGE_ALIGNED(bytes)) {
		dev_dbg(dev, "Found poison, but addr(%p) or bytes(%#zx) not page aligned\n",
			addr, bytes);
		return 0;
	}

	pmem_off = PFN_PHYS(pgoff) + pmem->data_offset;
	cleared = __pmem_clear_poison(pmem, pmem_off, len);
	if (cleared > 0 && cleared < len) {
		dev_dbg(dev, "poison cleared only %ld out of %zu bytes\n",
			cleared, len);
		return 0;
	}
	if (cleared < 0) {
		dev_dbg(dev, "poison clear failed: %ld\n", cleared);
		return 0;
	}

	olen = _copy_from_iter_flushcache(addr, bytes, i);
	pmem_clear_bb(pmem, to_sect(pmem, pmem_off), cleared >> SECTOR_SHIFT);

	return olen;
}

static const struct dax_operations pmem_dax_ops = {
	.direct_access = pmem_dax_direct_access,
	.zero_page_range = pmem_dax_zero_page_range,
	.recovery_write = pmem_recovery_write,
};

static ssize_t write_cache_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct pmem_device *pmem = dev_to_disk(dev)->private_data;

	return sprintf(buf, "%d\n", !!dax_write_cache_enabled(pmem->dax_dev));
}

static ssize_t write_cache_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
	struct pmem_device *pmem = dev_to_disk(dev)->private_data;
	bool write_cache;
	int rc;

	rc = strtobool(buf, &write_cache);
	if (rc)
		return rc;
	dax_write_cache(pmem->dax_dev, write_cache);
	return len;
}
static DEVICE_ATTR_RW(write_cache);

static umode_t dax_visible(struct kobject *kobj, struct attribute *a, int n)
{
#ifndef CONFIG_ARCH_HAS_PMEM_API
	if (a == &dev_attr_write_cache.attr)
		return 0;
#endif
	return a->mode;
}

static struct attribute *dax_attributes[] = {
	&dev_attr_write_cache.attr,
	NULL,
};

static const struct attribute_group dax_attribute_group = {
	.name		= "dax",
	.attrs		= dax_attributes,
	.is_visible	= dax_visible,
};

static const struct attribute_group *pmem_attribute_groups[] = {
	&dax_attribute_group,
	NULL,
};

static void pmem_release_disk(void *__pmem)
{
	struct pmem_device *pmem = __pmem;

	dax_remove_host(pmem->disk);
	kill_dax(pmem->dax_dev);
	put_dax(pmem->dax_dev);
	del_gendisk(pmem->disk);

	put_disk(pmem->disk);
}

static int pmem_pagemap_memory_failure(struct dev_pagemap *pgmap,
		unsigned long pfn, unsigned long nr_pages, int mf_flags)
{
	struct pmem_device *pmem =
			container_of(pgmap, struct pmem_device, pgmap);
	u64 offset = PFN_PHYS(pfn) - pmem->phys_addr - pmem->data_offset;
	u64 len = nr_pages << PAGE_SHIFT;

	return dax_holder_notify_failure(pmem->dax_dev, offset, len, mf_flags);
}

static const struct dev_pagemap_ops fsdax_pagemap_ops = {
	.memory_failure		= pmem_pagemap_memory_failure,
};

static int pmem_attach_disk(struct device *dev,
		struct nd_namespace_common *ndns)
{
	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
	struct nd_region *nd_region = to_nd_region(dev->parent);
	int nid = dev_to_node(dev), fua;
	struct resource *res = &nsio->res;
	struct range bb_range;
	struct nd_pfn *nd_pfn = NULL;
	struct dax_device *dax_dev;
	struct nd_pfn_sb *pfn_sb;
	struct pmem_device *pmem;
	struct request_queue *q;
	struct gendisk *disk;
	void *addr;
	int rc;

	pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL);
	if (!pmem)
		return -ENOMEM;

	rc = devm_namespace_enable(dev, ndns, nd_info_block_reserve());
	if (rc)
		return rc;

	/* while nsio_rw_bytes is active, parse a pfn info block if present */
	if (is_nd_pfn(dev)) {
		nd_pfn = to_nd_pfn(dev);
		rc = nvdimm_setup_pfn(nd_pfn, &pmem->pgmap);
		if (rc)
			return rc;
	}

	/* we're attaching a block device, disable raw namespace access */
	devm_namespace_disable(dev, ndns);

	dev_set_drvdata(dev, pmem);
	pmem->phys_addr = res->start;
	pmem->size = resource_size(res);
	fua = nvdimm_has_flush(nd_region);
	if (!IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) || fua < 0) {
		dev_warn(dev, "unable to guarantee persistence of writes\n");
		fua = 0;
	}

	if (!devm_request_mem_region(dev, res->start, resource_size(res),
				dev_name(&ndns->dev))) {
		dev_warn(dev, "could not reserve region %pR\n", res);
		return -EBUSY;
	}

	disk = blk_alloc_disk(nid);
	if (!disk)
		return -ENOMEM;
	q = disk->queue;

	pmem->disk = disk;
	pmem->pgmap.owner = pmem;
	pmem->pfn_flags = PFN_DEV;
	if (is_nd_pfn(dev)) {
		pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
		pmem->pgmap.ops = &fsdax_pagemap_ops;
		addr = devm_memremap_pages(dev, &pmem->pgmap);
		pfn_sb = nd_pfn->pfn_sb;
		pmem->data_offset = le64_to_cpu(pfn_sb->dataoff);
		pmem->pfn_pad = resource_size(res) -
			range_len(&pmem->pgmap.range);
		pmem->pfn_flags |= PFN_MAP;
		bb_range = pmem->pgmap.range;
		bb_range.start += pmem->data_offset;
	} else if (pmem_should_map_pages(dev)) {
		pmem->pgmap.range.start = res->start;
		pmem->pgmap.range.end = res->end;
		pmem->pgmap.nr_range = 1;
		pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
		pmem->pgmap.ops = &fsdax_pagemap_ops;
		addr = devm_memremap_pages(dev, &pmem->pgmap);
		pmem->pfn_flags |= PFN_MAP;
		bb_range = pmem->pgmap.range;
	} else {
		addr = devm_memremap(dev, pmem->phys_addr,
				pmem->size, ARCH_MEMREMAP_PMEM);
		bb_range.start =  res->start;
		bb_range.end = res->end;
	}

	if (IS_ERR(addr)) {
		rc = PTR_ERR(addr);
		goto out;
	}
	pmem->virt_addr = addr;

	blk_queue_write_cache(q, true, fua);
	blk_queue_physical_block_size(q, PAGE_SIZE);
	blk_queue_logical_block_size(q, pmem_sector_size(ndns));
	blk_queue_max_hw_sectors(q, UINT_MAX);
	blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
	if (pmem->pfn_flags & PFN_MAP)
		blk_queue_flag_set(QUEUE_FLAG_DAX, q);

	disk->fops		= &pmem_fops;
	disk->private_data	= pmem;
	nvdimm_namespace_disk_name(ndns, disk->disk_name);
	set_capacity(disk, (pmem->size - pmem->pfn_pad - pmem->data_offset)
			/ 512);
	if (devm_init_badblocks(dev, &pmem->bb))
		return -ENOMEM;
	nvdimm_badblocks_populate(nd_region, &pmem->bb, &bb_range);
	disk->bb = &pmem->bb;

	dax_dev = alloc_dax(pmem, &pmem_dax_ops);
	if (IS_ERR(dax_dev)) {
		rc = PTR_ERR(dax_dev);
		goto out;
	}
	set_dax_nocache(dax_dev);
	set_dax_nomc(dax_dev);
	if (is_nvdimm_sync(nd_region))
		set_dax_synchronous(dax_dev);
	rc = dax_add_host(dax_dev, disk);
	if (rc)
		goto out_cleanup_dax;
	dax_write_cache(dax_dev, nvdimm_has_cache(nd_region));
	pmem->dax_dev = dax_dev;

	rc = device_add_disk(dev, disk, pmem_attribute_groups);
	if (rc)
		goto out_remove_host;
	if (devm_add_action_or_reset(dev, pmem_release_disk, pmem))
		return -ENOMEM;

	nvdimm_check_and_set_ro(disk);

	pmem->bb_state = sysfs_get_dirent(disk_to_dev(disk)->kobj.sd,
					  "badblocks");
	if (!pmem->bb_state)
		dev_warn(dev, "'badblocks' notification disabled\n");
	return 0;

out_remove_host:
	dax_remove_host(pmem->disk);
out_cleanup_dax:
	kill_dax(pmem->dax_dev);
	put_dax(pmem->dax_dev);
out:
	put_disk(pmem->disk);
	return rc;
}

static int nd_pmem_probe(struct device *dev)
{
	int ret;
	struct nd_namespace_common *ndns;

	ndns = nvdimm_namespace_common_probe(dev);
	if (IS_ERR(ndns))
		return PTR_ERR(ndns);

	if (is_nd_btt(dev))
		return nvdimm_namespace_attach_btt(ndns);

	if (is_nd_pfn(dev))
		return pmem_attach_disk(dev, ndns);

	ret = devm_namespace_enable(dev, ndns, nd_info_block_reserve());
	if (ret)
		return ret;

	ret = nd_btt_probe(dev, ndns);
	if (ret == 0)
		return -ENXIO;

	/*
	 * We have two failure conditions here, there is no
	 * info reserver block or we found a valid info reserve block
	 * but failed to initialize the pfn superblock.
	 *
	 * For the first case consider namespace as a raw pmem namespace
	 * and attach a disk.
	 *
	 * For the latter, consider this a success and advance the namespace
	 * seed.
	 */
	ret = nd_pfn_probe(dev, ndns);
	if (ret == 0)
		return -ENXIO;
	else if (ret == -EOPNOTSUPP)
		return ret;

	ret = nd_dax_probe(dev, ndns);
	if (ret == 0)
		return -ENXIO;
	else if (ret == -EOPNOTSUPP)
		return ret;

	/* probe complete, attach handles namespace enabling */
	devm_namespace_disable(dev, ndns);

	return pmem_attach_disk(dev, ndns);
}

static void nd_pmem_remove(struct device *dev)
{
	struct pmem_device *pmem = dev_get_drvdata(dev);

	if (is_nd_btt(dev))
		nvdimm_namespace_detach_btt(to_nd_btt(dev));
	else {
		/*
		 * Note, this assumes device_lock() context to not
		 * race nd_pmem_notify()
		 */
		sysfs_put(pmem->bb_state);
		pmem->bb_state = NULL;
	}
	nvdimm_flush(to_nd_region(dev->parent), NULL);
}

static void nd_pmem_shutdown(struct device *dev)
{
	nvdimm_flush(to_nd_region(dev->parent), NULL);
}

static void pmem_revalidate_poison(struct device *dev)
{
	struct nd_region *nd_region;
	resource_size_t offset = 0, end_trunc = 0;
	struct nd_namespace_common *ndns;
	struct nd_namespace_io *nsio;
	struct badblocks *bb;
	struct range range;
	struct kernfs_node *bb_state;

	if (is_nd_btt(dev)) {
		struct nd_btt *nd_btt = to_nd_btt(dev);

		ndns = nd_btt->ndns;
		nd_region = to_nd_region(ndns->dev.parent);
		nsio = to_nd_namespace_io(&ndns->dev);
		bb = &nsio->bb;
		bb_state = NULL;
	} else {
		struct pmem_device *pmem = dev_get_drvdata(dev);

		nd_region = to_region(pmem);
		bb = &pmem->bb;
		bb_state = pmem->bb_state;

		if (is_nd_pfn(dev)) {
			struct nd_pfn *nd_pfn = to_nd_pfn(dev);
			struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;

			ndns = nd_pfn->ndns;
			offset = pmem->data_offset +
					__le32_to_cpu(pfn_sb->start_pad);
			end_trunc = __le32_to_cpu(pfn_sb->end_trunc);
		} else {
			ndns = to_ndns(dev);
		}

		nsio = to_nd_namespace_io(&ndns->dev);
	}

	range.start = nsio->res.start + offset;
	range.end = nsio->res.end - end_trunc;
	nvdimm_badblocks_populate(nd_region, bb, &range);
	if (bb_state)
		sysfs_notify_dirent(bb_state);
}

static void pmem_revalidate_region(struct device *dev)
{
	struct pmem_device *pmem;

	if (is_nd_btt(dev)) {
		struct nd_btt *nd_btt = to_nd_btt(dev);
		struct btt *btt = nd_btt->btt;

		nvdimm_check_and_set_ro(btt->btt_disk);
		return;
	}

	pmem = dev_get_drvdata(dev);
	nvdimm_check_and_set_ro(pmem->disk);
}

static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
{
	switch (event) {
	case NVDIMM_REVALIDATE_POISON:
		pmem_revalidate_poison(dev);
		break;
	case NVDIMM_REVALIDATE_REGION:
		pmem_revalidate_region(dev);
		break;
	default:
		dev_WARN_ONCE(dev, 1, "notify: unknown event: %d\n", event);
		break;
	}
}

MODULE_ALIAS("pmem");
MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_IO);
MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_PMEM);
static struct nd_device_driver nd_pmem_driver = {
	.probe = nd_pmem_probe,
	.remove = nd_pmem_remove,
	.notify = nd_pmem_notify,
	.shutdown = nd_pmem_shutdown,
	.drv = {
		.name = "nd_pmem",
	},
	.type = ND_DRIVER_NAMESPACE_IO | ND_DRIVER_NAMESPACE_PMEM,
};

module_nd_driver(nd_pmem_driver);

MODULE_AUTHOR("Ross Zwisler <ross.zwisler@linux.intel.com>");
MODULE_LICENSE("GPL v2");